4DAnyone turns single monocular video into 4D human models
janusch_patas · x · 2026-08-21
4DAnyone turns a casual monocular video into a 4D Gaussian Splatting (4DGS) model without the need for camera rigs, calibration, or tripods. The project, accepted by SIGGRAPH Asia 2026, addresses consistency challenges using Reference Context Packing (RCP) and Target Context Routing (TCR), while leveraging a 3D skeleton for robust geometric conditioning.
Related event: 4DAnyone Generates 4D Human Avatars from Monocular Video(3 posts)→
More from Multimodal
- MLP-Splatting (ECCV 2026) code released: MLPs as light-field primitives instead of Gaussians — AjdDavison · 2026-10-16
- Digital human Fae codes her own facial expressions frame-by-frame with Claude Opus 5.5 and FACS — repligate · 2026-10-16
- Meta's Omnilingual ASR, covering 1,600 languages, named a TIME Best Invention of 2026 — AIatMeta · 2026-10-16
- ATAS: Zhejiang-led team builds world-state memory framework for consistent agentic video generation — CSProfKGD · 2026-10-16
- Flux 3 Klein's Default Templates Are Broken Without Its Prompt Upscaler — StrictMove5839 · 2026-10-16
- Kroma Touted as the Most Well-Rounded Image Model Yet on Civitai — Different_Fix_2217 · 2026-10-16